383toast parent
They should've tested other embedding models, there are better ones than openai's (and cheaper)
Which do you suggest?
You should use RTEB instead. See here for why:
https://huggingface.co/blog/rteb
Here is that leaderboard https://huggingface.co/spaces/mteb/leaderboard?benchmark_nam...
Voyage-3-large seems like SOTA right now
yep
The Qwen3 600M and 4B embedding models are near state of the art and aren't too computationally intensive.